计算机应用与软件2024，Vol.41Issue(4)：224-227,274,5.DOI:10.3969/j.issn.1000-386x.2024.04.034
基于System Generator的卷积加速结构设计与实现
DESIGN AND IMPLEMENTATION OF CONVOLUTION ACCELERATION STRUCTURE BASED ON SYSTEM GENERATOR
摘要
Abstract
In order to solve the time-consuming and complicated operation problems in convolutional neural networks,this paper proposes a block-based pipeline acceleration method according to the parallelism characteristics of convolution operation,and designs the circuit on System Generator based on this method.Through the experimental verification on field-programmable gate array(FPGA),the design model can correctly output the convolution operation results.In the case of the same structure and input data,the design model can accelerate up to 258 times compared with ordinary CPU in calculation speed,and increase by nearly 40 times compared with server-level CPU,and has a good acceleration effect.关键词
卷积神经网络/卷积运算/System Generator/现场可编程门阵列Key words
Convolutional neural networks/Convolution operation/System Generator/FPGA分类
信息技术与安全科学引用本文复制引用
成鸿群,刘宜成,涂海燕,徐金鹏,王广泰..基于System Generator的卷积加速结构设计与实现[J].计算机应用与软件,2024,41(4):224-227,274,5.基金项目
国家自然科学基金项目(81803056). （81803056）
